Overview

This dashboard explores the musical properties of my AI-generated tracks using chromagrams, self-similarity matrices, and danceability analysis.

Chromagram

Chromagrams for own tracks

!!! I currently keep having issues with my chromagrams not loading (though they do show in R), so it may be that they don’t show up yet. Trying to fix this ASAP.

Chromagrams capture the harmonic content by showing how energy is distributed across the 12 pitch classes over time.

This took quite a lot of time to display this graphic, you may set 'fastdisp=TRUE' for a faster, but less accurate, display

Self-Similarity Matrices

AI-Generated Tracks

These tracks were created using Stableaudio AI (Stableaudio). I took inspiration from genre tags on RateYourMusic and carefully crafted prompts using detailed descriptors to shape the sound. After generating the tracks, I simply downloaded the MP3 files.

Track 1: Meditative Ambient Soundscape

Style: Ambient, Post-Rock, Cinematic
Length: 2 minutes
Goal: A calm, meditative ambient with minimal instrumentation.

Track 2: Energetic Breakbeat Rave

Style: Breakbeat, Acid Breaks, 90s Rave
Length: 2 minutes
Goal: A high-energy, chaotic breakbeat track.

Visualization

Here’s a scatterplot of the Danceability compared to the Tempo of the tracks. My track 1 (ambient) is marked red, track 2 (breakbeat) is blue.

Final Thoughts

There appears to be no set correlation between the danceability and tempo of the tracks. However, an interesting pattern emerges: there are two clusters—one with low danceability, and another with high danceability, while the tempo does not differ much.

Regarding my own tracks:

One particularly surprising observation is how the AI interpreted the second song’s tempo. While I set it to 135 BPM, it was classified as 93 BPM. This suggests that the AI might have emphasized a different rhythmic structure or half-time feel in its classification.